© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16997
    Prev
    Next
    INDEX
    Explanations

    example clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ëŀĮ
    -0.08
    ÑĥÑīе
    -0.08
    çļĦåIJĦ项
    -0.08
    åIJĦ项活åĬ¨
    -0.08
    åIJĦ项è§Ħç«łåĪ¶åº¦
    -0.08
    ErrorMsg
    -0.08
    orian
    -0.08
    truncate
    -0.08
    æĺ¯ä¸ĢåĪĩ
    -0.07
    å¦ĤåĪĿ
    -0.07
    POSITIVE LOGITS
    ä¸įèĥľ
    0.07
     themselves
    0.07
     коÑĤоÑĢÑĭе
    0.06
     коÑĤоÑĢÑĭми
    0.06
    uga
    0.06
     whose
    0.06
     that
    0.06
    pel
    0.06
    èĦijä¸Ń
    0.06
    åĩºèº«çļĦ
    0.06
    Activations Density 0.116%

    No Known Activations